Autonomous Systems Lab

Open Opportunities

LIDAR Odometry and State Estimation for Space Robotics applications ETH Zurich Autonomous Systems Lab Together with ESA and Beyond Gravity, we're developing a system for testing microgravity space structures on earth. To do so, we're developing reactive ground robots that are able to support e.g. solar panels while their unfolding from a satellite is tested. Your part of the project is to develop, evaluate and test (on the robot) state estimation solutions based on LIDAR and IMU. Intelligent Robotics Semester Project

Vison- and Depth-based Reinforcement Learning for dexterous and accurate manipulation with Aerial Robots [multiple openings] ETH Zurich Autonomous Systems Lab Our team develops novel Aerial Robots that are able to autonomously manipulate and perform work in flight. In this thesis, we would like to explore the learning of task-specific policies for manipulation in flight. Intelligent Robotics Master Thesis

Robust Reinforcement Learned Controllers for Aerial Robots ETH Zurich Autonomous Systems Lab Develop novel RL controllers for cutting-edge aerial robots that are able to do physical work. Intelligent Robotics Master Thesis

Factor-graph based state-estimation for Aerial Robots using novel sensors ETH Zurich Autonomous Systems Lab Algorithmically integrate a novel type of inertial sensor into our state estimation pipeline. Your results will be used to improve our cutting edge aerial robot. Intelligent Robotics Semester Project

Airflow Interaction Identification for an Omnidirectional Multicopter ETH Zurich Autonomous Systems Lab The Autonomous Systems Lab's (ASL) Omnidirectional Micro Aerial Vehicle (OMAV) tilts its propellers to generate thrust in any direction, at any orientation. This comes with the side-effect that propeller wash may blow over neighboring propellers, effecting their inflow, and thus the thrust each individual prop may produce. Airflow interaction is complex physical process which is very difficult to model. In this project, our aim is to design a suitable experimental test rig to collect data from the relevant range of interaction states and use machine learning techniques to identify a suitable model of the interaction effects on the OMAVs applied forces and torques. This model will enhance the realism of our simulation infrastructure as well as provide a more accurate model prior for future control and estimation pipelines. Aerodynamics, Intelligent Robotics Semester Project

Gaussian Belief Propagation using Bayes Models ETH Zurich Autonomous Systems Lab Gaussian Belief Propagation (GBP) has emerged as a promising factor graph inference method, offering remarkable scalability and flexibility, particularly in distributed optimization across multiple agents. However, GBP faces several significant challenges, including convergence issues, the dependency on reliable initial estimates, and the need for an efficient scheduling scheme to coordinate message passing. This thesis project aims to address these challenges by exploring the integration of Bayesian modeling into the GBP process, to improve initialization and scheduling, ultimately enhancing the robustness and effectiveness of GBP in practical applications. Computer Vision, Intelligent Robotics, Optimisation Master Thesis

Gaussian Belief Propagation for Distributed Visual-Inertial Continuous-Time SLAM across Multiple Autonomous Agents ETH Zurich Autonomous Systems Lab The emerging paradigm of Continuous-Time Simultaneous Localization And Mapping (CTSLAM) has become a competitive alternative to conventional discrete-time approaches in recent times and holds the additional promise of fusing multi-modal sensor setups in a truly generic manner, rendering its importance to robotic navigation and manipulation seminal. Based on our recent works, in this project, we aim to further investigate the concept of asynchronous, distributed continuous-time SLAM across multiple agents, which gives rise to several interesting and impact-full research questions in terms of convergence, efficiency, and achievable accuracy. With these high-level goals in mind, we are looking forward to individually discussing the available thesis topics in greater detail. Computer Vision, Intelligent Robotics, Stochastic Analysis and Modelling Master Thesis

Data-efficient learning of world models ETH Zurich Autonomous Systems Lab Model-based reinforcement learning uses world models to predict the outcomes of a robot's actions, allowing it to "imagine" new interaction trajectories and reduce data needs. However, learning a high-fidelity world model requires a large amount of data. This thesis aims to minimize the amount of real-world data required to learn a world model. We will stat experimenting with simple tasks, such as pushing objects on a table, and eventually test our ideas on a real robot arm. Computer Vision, Intelligent Robotics, Robotics and Mechatronics Master Thesis

Robust Graph Optimization for Robotic Perception ETH Zurich Autonomous Systems Lab Other organizations: Vision for Robotics Lab Graph optimization is a key technique employed within Simultaneous Localization And Mapping (SLAM) frameworks, enabling the automation of robot navigation. By encoding a mobile robot’s experiences of the world in a graph (i.e., the robot poses and the sensor readings), such techniques offer a robust way of estimating the robot’s trajectory and the map of its environment. However, these techniques are often computationally demanding and their performance is severely hampered by outliers originating from erroneous sensor measurements or incorrect loop closure detections. To address this challenge, robust graph optimization methods, such as Pairwise Consistency Maximisation (PCM) [2] and Graduated Non-Convexity (GNC) [3], have been devised aiming to enhance the resilience of SLAM algorithms against such outliers, however robustness and complexity both remain open challenges to date. This project aims to build on the strengths of existing works on robust graph optimization in the context of SLAM, and guide the development and implementation of optimization methods robust to outliers caused by erroneous measurements and loop closure detections. Moreover, techniques such as incremental computation will be investigated to better tailor graph optimization to real-time SLAM applications, which is a requirement in robot navigation. This project is offered by the Vision for Robotics Lab (www.v4rl.com) at ETH Zurich and the University of Cyprus. Students undertaking the project may have the opportunity to visit the lab at the University of Cyprus, but this is not required. Computer Vision, Intelligent Robotics, Robotics and Mechatronics Semester Project

Multi-Sensor Semantic Odometry ETH Zurich Autonomous Systems Lab Other organizations: Vision for Robotics Lab Semantic segmentation augments visual information from cameras or geometric information from LiDARs by classifying what objects are present in a scene. Fusing this semantic information with visual or geometric sensor data can improve the odometry estimate of a robot moving through the scene. Uni-modal semantic odometry approaches using camera images or LiDAR point clouds have been shown to outperform traditional single-sensor approaches. However, multi-sensor odometry approaches typically provide more robust estimation in degenerate environments. Computer Vision, Image Processing, Intelligent Robotics, Signal Processing Master Thesis, Semester Project